Skip to Main content Skip to Navigation
Conference papers

Efficient Wait-k Models for Simultaneous Machine Translation

Abstract : Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they alternate between producing a target token and reading another source token. We investigate the behavior of wait-k decoding in low resource settings for spoken corpora using IWSLT datasets. We improve training of these models using unidirectional encoders, and training across multiple values of k. Experiments with Transformer and 2D-convolutional architectures show that our wait-k models generalize well across a wide range of latency levels. We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language.
Document type :
Conference papers
Complete list of metadata

Cited literature [30 references]  Display  Hide  Download
Contributor : Laurent Besacier Connect in order to contact the contributor
Submitted on : Friday, October 9, 2020 - 9:04:41 AM
Last modification on : Wednesday, July 6, 2022 - 4:17:45 AM
Long-term archiving on: : Sunday, January 10, 2021 - 6:14:18 PM


Files produced by the author(s)



Maha Elbayad, Laurent Besacier, Jakob Verbeek. Efficient Wait-k Models for Simultaneous Machine Translation. Interspeech 2020 - Conference of the International Speech Communication Association, Oct 2020, Shangai (Virtual Conf), China. pp.1461--1465, ⟨10.21437/Interspeech.2020-1241⟩. ⟨hal-02962195⟩



Record views


Files downloads